Local features and matching. Image classification & object localization
|
|
|
- Shannon Webb
- 10 years ago
- Views:
Transcription
1 Overview Instance level search Local features and matching Efficient visual recognition Image classification & object localization
2 Category recognition Image classification: assigning a class label to the image Car: present Cow: present Bike: not present Horse: not present
3 Category Tasks recognition Image classification: assigning a class label to the image Car: present Cow: present Bike: not present Horse: not present Object localization: define the location and the category Car Cow Location Category
4 Given Image classification Positive training images containing an object class Negative training images that don t Classify A test image as to whether it contains the object class or not?
5 Bag-of-features features for image classification Origin: texture recognition Texture is characterized by the repetition of basic elements or textons Julesz, 1981; Cula & Dana, 2001; Leung & Malik 2001; Mori, Belongie & Malik, 2001; Schmid 2001; Varma & Zisserman, 2002, 2003; Lazebnik, Schmid & Ponce, 2003
6 Texture recognition histogram Universal texton dictionary Julesz, 1981; Cula & Dana, 2001; Leung & Malik 2001; Mori, Belongie & Malik, 2001; Schmid 2001; Varma & Zisserman, 2002, 2003; Lazebnik, Schmid & Ponce, 2003
7 Bag-of-features features Origin: bag-of-words (text) Orderless document representation: frequencies of words from a dictionary Classification to determine document categories Bag-of-words Common o People Sculpture
8 Bag-of-features features for image classification SVM Extract regions Compute Find clusters Compute distance Classification descriptors and frequencies matrix [Nowak,Jurie&Triggs,ECCV 06], [Zhang,Marszalek,Lazebnik&Schmid,IJCV 07]
9 Bag-of-features features for image classification SVM Extract regions Compute Find clusters Compute distance Classification descriptors and frequencies matrix Step 1 Step 2 Step 3 [Nowak,Jurie&Triggs,ECCV 06], [Zhang,Marszalek,Lazebnik&Schmid,IJCV 07]
10 Step 1: feature extraction Scale-invariant image regions + SIFT Rotation invariance for many realistic collections too much invariance Dense descriptors Improve results in the context of categories (for most categories) Interest points do not necessarily capture all features Color-based descriptors Shape-based descriptors
11 Dense features - Multi-scale dense grid: extraction of small overlapping patches at multiple scales -Computation of the SIFT descriptor for each grid cells -Exp.: Horizontal/vertical step size 6 pixel, scaling factor of 1.2 per level
12 Bag-of-features features for image classification SVM Extract regions Compute Find clusters Compute distance Classification descriptors and frequencies matrix Step 1 Step 2 Step 3
13 Step 2: Quantization
14 Step 2:Quantization Clustering
15 Step 2: Quantization Visual vocabulary Clustering
16 Airplanes Motorbikes Faces Wild Cats Leaves People Bikes Examples for visual words
17 Step 2: Quantization Cluster descriptors K-means Gaussian mixture model Assign each visual word to a cluster Hard or soft assignment Build frequency histogram
18 Hard or soft assignment K-means hard assignment Assign to the closest cluster center Count number of descriptors assigned to a center Gaussian mixture model soft assignment Estimate distance to all centers Sum over number of descriptors Represent image by a frequency histogram
19 Image representation fr requenc cy.. codewords Each image is represented by a vector, typically dimension, normalization with L2 norm fine grained represent model instances coarse grained represent object categories
20 Bag-of-features features for image classification SVM Extract regions Compute Find clusters Compute distance Classification descriptors and frequencies matrix Step 1 Step 2 Step 3
21 Step 3: Classification Learn a decision rule (classifier) assigning bag-of- features representations of images to different classes Decision boundary Zebra Non-zebra
22 Training data Vectors are histograms, one from each training image positive negative Train classifier,e.g.svm
23 Classifiers K-nearest neighbor classifier Linear classifier Support Vector Machine Non-linear classifier Kernel trick Explicit lifting
24 Classification Assign input vector to one of two or more classes Any decision rule divides input space into decision regions separated by decision boundaries
25 Nearest Neighbor Classifier Assign label of nearest training data point to each test data point from Duda et al. Voronoi partitioning of feature space for 2-category 2-D and 3-D data
26 k-nearest Neighbors For a new point, find the k closest points from training data Labels of the k points vote to classify Works well provided there is lots of data and the distance function is good k =5
27 Linear classifiers Find linear function (hyperplane) to separate positive and negative examples x x i i positive : negative : x x i i w w b b 0 0 Which hyperplane is best?
28 Linear classifiers - margin x 2 (color) Generalization is not good in this case: x1(roundness) 1 Better if a margin is introduced: b/ w x 2 (color) x1(roundness) 1
29 Support vector machines Find hyperplane that maximizes the margin between the positive and negative examples x positive ( y 1) : x w b x i i negative( i y i 1) : x i i w b 1 1 For support, vectors, x i w b 1 i The margin is 2 / w Support vectors Margin
30 Nonlinear SVMs Datasets that are linearly separable work out great: 0 x But what if the dataset is just too hard? 0 x We can map it to a higher-dimensional space: x 2 0 x
31 Nonlinear SVMs General idea: the original input space can always be mapped to some higher-dimensional feature space where the training set is separable: Φ: x φ(x)
32 Nonlinear SVMs The kernel trick: instead of explicitly computing the lifting transformation φ(x), define a kernel function K such that K(x i,x j j) = φ(x i ) φ(x j ) This gives a nonlinear decision boundary in the original feature e space: i yik ( xi, x ) i b
33 Kernels for bags of features Kernels for bags of features Hellinger kernel N i h i h h h K ) ( ) ( ) ( Hellinger kernel i i h i h h h K ) ( ) ( ), ( Histogram intersection kernel N i i h i h h h I )) ( ), ( min( ), ( Generalized Gaussian kernel i 1 2 ) ( 1 exp ) ( h h D h h K Generalized Gaussian kernel D can be Euclidean distance, χ 2 distance etc ), ( exp ), ( h h D A h h K D can be Euclidean distance, χ distance etc. N i h i h h h D ) ( ) ( ), ( 2 i i h i h ) ( ) ( ), ( 2
34 Multi-class SVMs Various direct formulations exist, but they are not widely used in practice. It is more common to obtain multi-class SVMs by combining two-class SVMs in various ways. One versus all: Training: learn an SVM for each class versus the others Testing: apply each SVM to test example and assign to it the class of the SVM that returns the highest decision value One versus one: Training: learn an SVM for each pair of classes Testing: each learned SVM votes for a class to assign to the test example
35 Why does SVM learning work? Learns foreground and background visual words foreground words high weight background words low weight
36 Illustration Localization according to visual word probability Correct Image: 35 Correct Image: Correct Image: 38 Correct Image: foreground word more probable background word more probable
37 Illustration A linear SVM trained from positive and negative window descriptors A few of the highest weighed descriptor vector dimensions (= 'PAS + tile') + lie on object boundary (= local shape structures common to many training exemplars)
38 Bag-of-features features for image classification Excellent results in the presence of background clutter bikes books building cars people phones trees
39 Examples for misclassified images Books- misclassified into faces, faces, buildings Buildings- misclassified into faces, trees, trees Cars- misclassified into buildings, phones, phones
40 Bag of visual words summary Advantages: largely unaffected by position and orientation of object in image fixed length vector irrespective of number of detections very successful in classifying images according to the objects they contain Disadvantages: no explicit use of configuration of visual word positions poor at localizing objects within an image
41 Evaluation of image classification PASCAL VOC [05-10] datasets PASCAL VOC 2007 Training and test dataset available Used to report state-of-the-art the art results Collected January 2007 from Flickr images downloaded and random subset selected 20 classes Class labels per image + bounding boxes 5011 training i images, 4952 test t images Evaluation measure: average precision
42 PASCAL 2007 dataset
43 PASCAL 2007 dataset
44 Evaluation
45 Overview Instance level search Local features and matching Efficient visual recognition Image classification & object localization
46 Recognition Classification Object present/absent in an image Often presence of a significant amount of background clutter Localization / Detection Localize object within the frame Bounding box or pixellevel segmentation
47 Pixel-level level object classification
48 Difficulties Intra-class variations Scale and viewpoint change Multiple aspects of categories
49 Approaches Intra-class variation => Modeling of the variations, mainly by learning from a large dataset, for example by SVMs Scale + limited viewpoints changes => multi-scale approach or invariant local features Multiple aspects of categories => separate detectors for each aspect, front/profile face, build an approximate 3D category model
50 Approaches Localization (bounding box) Sliding window approach Localization (segmentation) Pixel-based +MRF
51 Training Localization with sliding window Positive examples Negative examples Description + Learn a classifier
52 Localization with sliding window Testing at multiple l locations and scales Find local maxima, non-maxima suppression
53 Haar Wavelet / SVM Human Detector Haar wavelet descriptors Training set (2k positive / 10k negative) training 1326-D descriptor descriptors test Support vector machine results Test image [Papageorgiou & Poggio, 1998] Multi-scale search 53
54 Which Descriptors s are Important? 32x32 descriptors 16x16 descriptors Mean response difference between positive & negative training examples Essentially just a coarse-scale human silhouette template!
55 Some Detection Results
56 The Viola/Jones Face Detector A seminal approach to real-time object detection Training is slow, but detection is very fast Key ideas Integral images for fast feature evaluation Boosting for feature selection Attentional cascade for fast rejection of non-face windows P. Viola and M. Jones. Rapid object detection using a boosted cascade of simple features. CVPR P. Viola and M. Jones. Robust real-time face detection. IJCV 57(2), 2004.
57 Image Features Rectangle filters Value = (pixels in white area) (pixels in white area) (pixels in black area)
58 Fast computation with integral images The integral image computes a value at each pixel (x,y) that is the sum (x,y) of the pixel values above and to the left of (x,y), inclusive This can quickly be computed in one pass through the image
59 Feature selection For a 24x24 detection region, the number of possible rectangle features is ~160,000!
60 Feature selection For a 24x24 detection region, the number of possible rectangle features is ~160,000! At test time, it is impractical to evaluate the entire feature set Can we create a good classifier using just a small subset of all possible features? How to select such a subset?
61 Boosting Boosting is a classification scheme that works by combining weak learners into a more accurate ensemble classifier Training consists of multiple boosting rounds During each boosting round, we select a weak learner that does well on examples that were hard for the previous weak learners Hardness is captured by weights attached to training examples Y. Freund and R. Schapire, A short introduction to boosting, Journal of Japanese Society for Artificial Intelligence, 14(5): , September, 1999.
62 Boosting for face detection First two features selected by boosting: This feature combination can yield 100% s eatu e co b at o ca y e d 00% detection rate and 50% false positive rate
63 Attentional cascade We start with simple classifiers which reject many of the negative sub-windows while detecting almost all positive sub-windows Positive response from the first classifier triggers the evaluation of a second (more complex) classifier, and so on A negative outcome at any point leads to the immediate rejection of the sub-window IMAGE SUB-WINDOW Classifier 1 T Classifier 2 T Classifier 3 T FACE F F F NON-FACE NON-FACE NON-FACE
64 The implemented system Training Data 5000 faces All frontal, rescaled to 24x24 pixels 300 million non-faces 9500 non-face images Faces are normalized Scale, translation Many variations Across individuals Illumination Pose
65 Result of Face Detector on Test Images
66 Profile Detection
67 Profile Features
68 Summary: Viola/Jones detector Rectangle features Integral images for fast computation ti Boosting for feature selection Attentional cascade for fast rejection of negative windows Available in open CV
69 Histogram of Oriented Gradient Human Detector Descriptors are a grid of local Histograms of Oriented Gradients (HOG) Linear SVM for runtime efficiency Tolerates different poses, clothing, lighting and background Assumes upright fully visible people Importance weighted responses 69 [Dalal & Triggs, CVPR 2005]
70 Human detection
Robust Real-Time Face Detection
Robust Real-Time Face Detection International Journal of Computer Vision 57(2), 137 154, 2004 Paul Viola, Michael Jones 授 課 教 授 : 林 信 志 博 士 報 告 者 : 林 宸 宇 報 告 日 期 :96.12.18 Outline Introduction The Boost
Recognizing Cats and Dogs with Shape and Appearance based Models. Group Member: Chu Wang, Landu Jiang
Recognizing Cats and Dogs with Shape and Appearance based Models Group Member: Chu Wang, Landu Jiang Abstract Recognizing cats and dogs from images is a challenging competition raised by Kaggle platform
Cees Snoek. Machine. Humans. Multimedia Archives. Euvision Technologies The Netherlands. University of Amsterdam The Netherlands. Tree.
Visual search: what's next? Cees Snoek University of Amsterdam The Netherlands Euvision Technologies The Netherlands Problem statement US flag Tree Aircraft Humans Dog Smoking Building Basketball Table
Probabilistic Latent Semantic Analysis (plsa)
Probabilistic Latent Semantic Analysis (plsa) SS 2008 Bayesian Networks Multimedia Computing, Universität Augsburg [email protected] www.multimedia-computing.{de,org} References
The Delicate Art of Flower Classification
The Delicate Art of Flower Classification Paul Vicol Simon Fraser University University Burnaby, BC [email protected] Note: The following is my contribution to a group project for a graduate machine learning
Visual Categorization with Bags of Keypoints
Visual Categorization with Bags of Keypoints Gabriella Csurka, Christopher R. Dance, Lixin Fan, Jutta Willamowski, Cédric Bray Xerox Research Centre Europe 6, chemin de Maupertuis 38240 Meylan, France
Practical Tour of Visual tracking. David Fleet and Allan Jepson January, 2006
Practical Tour of Visual tracking David Fleet and Allan Jepson January, 2006 Designing a Visual Tracker: What is the state? pose and motion (position, velocity, acceleration, ) shape (size, deformation,
Semantic Recognition: Object Detection and Scene Segmentation
Semantic Recognition: Object Detection and Scene Segmentation Xuming He [email protected] Computer Vision Research Group NICTA Robotic Vision Summer School 2015 Acknowledgement: Slides from Fei-Fei
Automatic 3D Reconstruction via Object Detection and 3D Transformable Model Matching CS 269 Class Project Report
Automatic 3D Reconstruction via Object Detection and 3D Transformable Model Matching CS 69 Class Project Report Junhua Mao and Lunbo Xu University of California, Los Angeles [email protected] and lunbo
Object class recognition using unsupervised scale-invariant learning
Object class recognition using unsupervised scale-invariant learning Rob Fergus Pietro Perona Andrew Zisserman Oxford University California Institute of Technology Goal Recognition of object categories
3D Model based Object Class Detection in An Arbitrary View
3D Model based Object Class Detection in An Arbitrary View Pingkun Yan, Saad M. Khan, Mubarak Shah School of Electrical Engineering and Computer Science University of Central Florida http://www.eecs.ucf.edu/
Active Learning with Boosting for Spam Detection
Active Learning with Boosting for Spam Detection Nikhila Arkalgud Last update: March 22, 2008 Active Learning with Boosting for Spam Detection Last update: March 22, 2008 1 / 38 Outline 1 Spam Filters
Lecture 2: The SVM classifier
Lecture 2: The SVM classifier C19 Machine Learning Hilary 2015 A. Zisserman Review of linear classifiers Linear separability Perceptron Support Vector Machine (SVM) classifier Wide margin Cost function
IMPLICIT SHAPE MODELS FOR OBJECT DETECTION IN 3D POINT CLOUDS
IMPLICIT SHAPE MODELS FOR OBJECT DETECTION IN 3D POINT CLOUDS Alexander Velizhev 1 (presenter) Roman Shapovalov 2 Konrad Schindler 3 1 Hexagon Technology Center, Heerbrugg, Switzerland 2 Graphics & Media
Introduction to Support Vector Machines. Colin Campbell, Bristol University
Introduction to Support Vector Machines Colin Campbell, Bristol University 1 Outline of talk. Part 1. An Introduction to SVMs 1.1. SVMs for binary classification. 1.2. Soft margins and multi-class classification.
Recognition. Sanja Fidler CSC420: Intro to Image Understanding 1 / 28
Recognition Topics that we will try to cover: Indexing for fast retrieval (we still owe this one) History of recognition techniques Object classification Bag-of-words Spatial pyramids Neural Networks Object
Randomized Trees for Real-Time Keypoint Recognition
Randomized Trees for Real-Time Keypoint Recognition Vincent Lepetit Pascal Lagger Pascal Fua Computer Vision Laboratory École Polytechnique Fédérale de Lausanne (EPFL) 1015 Lausanne, Switzerland Email:
Convolutional Feature Maps
Convolutional Feature Maps Elements of efficient (and accurate) CNN-based object detection Kaiming He Microsoft Research Asia (MSRA) ICCV 2015 Tutorial on Tools for Efficient Object Detection Overview
Support Vector Machine (SVM)
Support Vector Machine (SVM) CE-725: Statistical Pattern Recognition Sharif University of Technology Spring 2013 Soleymani Outline Margin concept Hard-Margin SVM Soft-Margin SVM Dual Problems of Hard-Margin
Classification using Intersection Kernel Support Vector Machines is Efficient
To Appear in IEEE Computer Vision and Pattern Recognition 28, Anchorage Classification using Intersection Kernel Support Vector Machines is Efficient Subhransu Maji EECS Department U.C. Berkeley [email protected]
Class #6: Non-linear classification. ML4Bio 2012 February 17 th, 2012 Quaid Morris
Class #6: Non-linear classification ML4Bio 2012 February 17 th, 2012 Quaid Morris 1 Module #: Title of Module 2 Review Overview Linear separability Non-linear classification Linear Support Vector Machines
Semantic Image Segmentation and Web-Supervised Visual Learning
Semantic Image Segmentation and Web-Supervised Visual Learning Florian Schroff Andrew Zisserman University of Oxford, UK Antonio Criminisi Microsoft Research Ltd, Cambridge, UK Outline Part I: Semantic
Support Vector Machines with Clustering for Training with Very Large Datasets
Support Vector Machines with Clustering for Training with Very Large Datasets Theodoros Evgeniou Technology Management INSEAD Bd de Constance, Fontainebleau 77300, France [email protected] Massimiliano
Object Categorization using Co-Occurrence, Location and Appearance
Object Categorization using Co-Occurrence, Location and Appearance Carolina Galleguillos Andrew Rabinovich Serge Belongie Department of Computer Science and Engineering University of California, San Diego
Finding people in repeated shots of the same scene
Finding people in repeated shots of the same scene Josef Sivic 1 C. Lawrence Zitnick Richard Szeliski 1 University of Oxford Microsoft Research Abstract The goal of this work is to find all occurrences
A Study on SURF Algorithm and Real-Time Tracking Objects Using Optical Flow
, pp.233-237 http://dx.doi.org/10.14257/astl.2014.51.53 A Study on SURF Algorithm and Real-Time Tracking Objects Using Optical Flow Giwoo Kim 1, Hye-Youn Lim 1 and Dae-Seong Kang 1, 1 Department of electronices
Segmentation & Clustering
EECS 442 Computer vision Segmentation & Clustering Segmentation in human vision K-mean clustering Mean-shift Graph-cut Reading: Chapters 14 [FP] Some slides of this lectures are courtesy of prof F. Li,
Analysis of kiva.com Microlending Service! Hoda Eydgahi Julia Ma Andy Bardagjy December 9, 2010 MAS.622j
Analysis of kiva.com Microlending Service! Hoda Eydgahi Julia Ma Andy Bardagjy December 9, 2010 MAS.622j What is Kiva? An organization that allows people to lend small amounts of money via the Internet
MVA ENS Cachan. Lecture 2: Logistic regression & intro to MIL Iasonas Kokkinos [email protected]
Machine Learning for Computer Vision 1 MVA ENS Cachan Lecture 2: Logistic regression & intro to MIL Iasonas Kokkinos [email protected] Department of Applied Mathematics Ecole Centrale Paris Galen
Modelling, Extraction and Description of Intrinsic Cues of High Resolution Satellite Images: Independent Component Analysis based approaches
Modelling, Extraction and Description of Intrinsic Cues of High Resolution Satellite Images: Independent Component Analysis based approaches PhD Thesis by Payam Birjandi Director: Prof. Mihai Datcu Problematic
The use of computer vision technologies to augment human monitoring of secure computing facilities
The use of computer vision technologies to augment human monitoring of secure computing facilities Marius Potgieter School of Information and Communication Technology Nelson Mandela Metropolitan University
The Visual Internet of Things System Based on Depth Camera
The Visual Internet of Things System Based on Depth Camera Xucong Zhang 1, Xiaoyun Wang and Yingmin Jia Abstract The Visual Internet of Things is an important part of information technology. It is proposed
Who are you? Learning person specific classifiers from video
Who are you? Learning person specific classifiers from video Josef Sivic, Mark Everingham 2 and Andrew Zisserman 3 INRIA, WILLOW Project, Laboratoire d Informatique de l Ecole Normale Superieure, Paris,
Image Classification for Dogs and Cats
Image Classification for Dogs and Cats Bang Liu, Yan Liu Department of Electrical and Computer Engineering {bang3,yan10}@ualberta.ca Kai Zhou Department of Computing Science [email protected] Abstract
PATTERN RECOGNITION AND MACHINE LEARNING CHAPTER 4: LINEAR MODELS FOR CLASSIFICATION
PATTERN RECOGNITION AND MACHINE LEARNING CHAPTER 4: LINEAR MODELS FOR CLASSIFICATION Introduction In the previous chapter, we explored a class of regression models having particularly simple analytical
Group Sparse Coding. Fernando Pereira Google Mountain View, CA [email protected]. Dennis Strelow Google Mountain View, CA strelow@google.
Group Sparse Coding Samy Bengio Google Mountain View, CA [email protected] Fernando Pereira Google Mountain View, CA [email protected] Yoram Singer Google Mountain View, CA [email protected] Dennis Strelow
Data Mining Practical Machine Learning Tools and Techniques
Ensemble learning Data Mining Practical Machine Learning Tools and Techniques Slides for Chapter 8 of Data Mining by I. H. Witten, E. Frank and M. A. Hall Combining multiple models Bagging The basic idea
Point Matching as a Classification Problem for Fast and Robust Object Pose Estimation
Point Matching as a Classification Problem for Fast and Robust Object Pose Estimation Vincent Lepetit Julien Pilet Pascal Fua Computer Vision Laboratory Swiss Federal Institute of Technology (EPFL) 1015
Social Media Mining. Data Mining Essentials
Introduction Data production rate has been increased dramatically (Big Data) and we are able store much more data than before E.g., purchase data, social media data, mobile phone data Businesses and customers
Discovering objects and their location in images
Discovering objects and their location in images Josef Sivic Bryan C. Russell Alexei A. Efros Andrew Zisserman William T. Freeman Dept. of Engineering Science CS and AI Laboratory School of Computer Science
Artificial Neural Networks and Support Vector Machines. CS 486/686: Introduction to Artificial Intelligence
Artificial Neural Networks and Support Vector Machines CS 486/686: Introduction to Artificial Intelligence 1 Outline What is a Neural Network? - Perceptron learners - Multi-layer networks What is a Support
Boosting. [email protected]
. Machine Learning Boosting Prof. Dr. Martin Riedmiller AG Maschinelles Lernen und Natürlichsprachliche Systeme Institut für Informatik Technische Fakultät Albert-Ludwigs-Universität Freiburg [email protected]
Segmentation as Selective Search for Object Recognition
Segmentation as Selective Search for Object Recognition Koen E. A. van de Sande Jasper R. R. Uijlings Theo Gevers Arnold W. M. Smeulders University of Amsterdam University of Trento Amsterdam, The Netherlands
Interactive Offline Tracking for Color Objects
Interactive Offline Tracking for Color Objects Yichen Wei Jian Sun Xiaoou Tang Heung-Yeung Shum Microsoft Research Asia, Beijing, China {yichenw,jiansun,xitang,hshum}@microsoft.com Abstract In this paper,
Part-Based Recognition
Part-Based Recognition Benedict Brown CS597D, Fall 2003 Princeton University CS 597D, Part-Based Recognition p. 1/32 Introduction Many objects are made up of parts It s presumably easier to identify simple
A Learning Based Method for Super-Resolution of Low Resolution Images
A Learning Based Method for Super-Resolution of Low Resolution Images Emre Ugur June 1, 2004 [email protected] Abstract The main objective of this project is the study of a learning based method
VEHICLE LOCALISATION AND CLASSIFICATION IN URBAN CCTV STREAMS
VEHICLE LOCALISATION AND CLASSIFICATION IN URBAN CCTV STREAMS Norbert Buch 1, Mark Cracknell 2, James Orwell 1 and Sergio A. Velastin 1 1. Kingston University, Penrhyn Road, Kingston upon Thames, KT1 2EE,
Mean Shift Based Clustering in High Dimensions: A Texture Classification Example
Mean Shift Based Clustering in High Dimensions: A Texture Classification Example Bogdan Georgescu µ Ilan Shimshoni µ Peter Meer ¾µ Computer Science µ Electrical and Computer Engineering ¾µ Rutgers University,
Classifying Manipulation Primitives from Visual Data
Classifying Manipulation Primitives from Visual Data Sandy Huang and Dylan Hadfield-Menell Abstract One approach to learning from demonstrations in robotics is to make use of a classifier to predict if
Big Data: Image & Video Analytics
Big Data: Image & Video Analytics How it could support Archiving & Indexing & Searching Dieter Haas, IBM Deutschland GmbH The Big Data Wave 60% of internet traffic is multimedia content (images and videos)
Open-Set Face Recognition-based Visitor Interface System
Open-Set Face Recognition-based Visitor Interface System Hazım K. Ekenel, Lorant Szasz-Toth, and Rainer Stiefelhagen Computer Science Department, Universität Karlsruhe (TH) Am Fasanengarten 5, Karlsruhe
View-Invariant Dynamic Texture Recognition using a Bag of Dynamical Systems
View-Invariant Dynamic Texture Recognition using a Bag of Dynamical Systems Avinash Ravichandran, Rizwan Chaudhry and René Vidal Center for Imaging Science, Johns Hopkins University, Baltimore, MD 21218,
SZTAKI @ ImageCLEF 2011
SZTAKI @ ImageCLEF 2011 Bálint Daróczy Róbert Pethes András A. Benczúr Data Mining and Web search Research Group, Informatics Laboratory Computer and Automation Research Institute of the Hungarian Academy
Object Recognition. Selim Aksoy. Bilkent University [email protected]
Image Classification and Object Recognition Selim Aksoy Department of Computer Engineering Bilkent University [email protected] Image classification Image (scene) classification is a fundamental
Ensemble Methods. Knowledge Discovery and Data Mining 2 (VU) (707.004) Roman Kern. KTI, TU Graz 2015-03-05
Ensemble Methods Knowledge Discovery and Data Mining 2 (VU) (707004) Roman Kern KTI, TU Graz 2015-03-05 Roman Kern (KTI, TU Graz) Ensemble Methods 2015-03-05 1 / 38 Outline 1 Introduction 2 Classification
RANDOM PROJECTIONS FOR SEARCH AND MACHINE LEARNING
= + RANDOM PROJECTIONS FOR SEARCH AND MACHINE LEARNING Stefan Savev Berlin Buzzwords June 2015 KEYWORD-BASED SEARCH Document Data 300 unique words per document 300 000 words in vocabulary Data sparsity:
Making Sense of the Mayhem: Machine Learning and March Madness
Making Sense of the Mayhem: Machine Learning and March Madness Alex Tran and Adam Ginzberg Stanford University [email protected] [email protected] I. Introduction III. Model The goal of our research
Automated Attendance Management System using Face Recognition
Automated Attendance Management System using Face Recognition Mrunmayee Shirodkar Varun Sinha Urvi Jain Bhushan Nemade Student, Thakur College Of Student, Thakur College Of Student, Thakur College of Assistant
Multi-class Classification: A Coding Based Space Partitioning
Multi-class Classification: A Coding Based Space Partitioning Sohrab Ferdowsi, Svyatoslav Voloshynovskiy, Marcin Gabryel, and Marcin Korytkowski University of Geneva, Centre Universitaire d Informatique,
Search Taxonomy. Web Search. Search Engine Optimization. Information Retrieval
Information Retrieval INFO 4300 / CS 4300! Retrieval models Older models» Boolean retrieval» Vector Space model Probabilistic Models» BM25» Language models Web search» Learning to Rank Search Taxonomy!
Lecture 6: CNNs for Detection, Tracking, and Segmentation Object Detection
CSED703R: Deep Learning for Visual Recognition (206S) Lecture 6: CNNs for Detection, Tracking, and Segmentation Object Detection Bohyung Han Computer Vision Lab. [email protected] 2 3 Object detection
Machine Learning Final Project Spam Email Filtering
Machine Learning Final Project Spam Email Filtering March 2013 Shahar Yifrah Guy Lev Table of Content 1. OVERVIEW... 3 2. DATASET... 3 2.1 SOURCE... 3 2.2 CREATION OF TRAINING AND TEST SETS... 4 2.3 FEATURE
Classification of Fingerprints. Sarat C. Dass Department of Statistics & Probability
Classification of Fingerprints Sarat C. Dass Department of Statistics & Probability Fingerprint Classification Fingerprint classification is a coarse level partitioning of a fingerprint database into smaller
Blocks that Shout: Distinctive Parts for Scene Classification
Blocks that Shout: Distinctive Parts for Scene Classification Mayank Juneja 1 Andrea Vedaldi 2 C. V. Jawahar 1 Andrew Zisserman 2 1 Center for Visual Information Technology, International Institute of
EXPLORING IMAGE-BASED CLASSIFICATION TO DETECT VEHICLE MAKE AND MODEL FINAL REPORT
EXPLORING IMAGE-BASED CLASSIFICATION TO DETECT VEHICLE MAKE AND MODEL FINAL REPORT Jeffrey B. Flora, Mahbubul Alam, Amr H. Yousef, and Khan M. Iftekharuddin December 2013 DISCLAIMER The contents of this
High Level Describable Attributes for Predicting Aesthetics and Interestingness
High Level Describable Attributes for Predicting Aesthetics and Interestingness Sagnik Dhar Vicente Ordonez Tamara L Berg Stony Brook University Stony Brook, NY 11794, USA [email protected] Abstract
Multi-View Object Class Detection with a 3D Geometric Model
Multi-View Object Class Detection with a 3D Geometric Model Joerg Liebelt IW-SI, EADS Innovation Works D-81663 Munich, Germany [email protected] Cordelia Schmid LEAR, INRIA Grenoble F-38330 Montbonnot,
Signature Segmentation and Recognition from Scanned Documents
Signature Segmentation and Recognition from Scanned Documents Ranju Mandal, Partha Pratim Roy, Umapada Pal and Michael Blumenstein School of Information and Communication Technology, Griffith University,
The Scientific Data Mining Process
Chapter 4 The Scientific Data Mining Process When I use a word, Humpty Dumpty said, in rather a scornful tone, it means just what I choose it to mean neither more nor less. Lewis Carroll [87, p. 214] In
Jiří Matas. Hough Transform
Hough Transform Jiří Matas Center for Machine Perception Department of Cybernetics, Faculty of Electrical Engineering Czech Technical University, Prague Many slides thanks to Kristen Grauman and Bastian
Data Mining. Nonlinear Classification
Data Mining Unit # 6 Sajjad Haider Fall 2014 1 Nonlinear Classification Classes may not be separable by a linear boundary Suppose we randomly generate a data set as follows: X has range between 0 to 15
Tracking in flussi video 3D. Ing. Samuele Salti
Seminari XXIII ciclo Tracking in flussi video 3D Ing. Tutors: Prof. Tullio Salmon Cinotti Prof. Luigi Di Stefano The Tracking problem Detection Object model, Track initiation, Track termination, Tracking
Environmental Remote Sensing GEOG 2021
Environmental Remote Sensing GEOG 2021 Lecture 4 Image classification 2 Purpose categorising data data abstraction / simplification data interpretation mapping for land cover mapping use land cover class
How To Use A Near Neighbor To A Detector
Ensemble of -SVMs for Object Detection and Beyond Tomasz Malisiewicz Carnegie Mellon University Abhinav Gupta Carnegie Mellon University Alexei A. Efros Carnegie Mellon University Abstract This paper proposes
Mean-Shift Tracking with Random Sampling
1 Mean-Shift Tracking with Random Sampling Alex Po Leung, Shaogang Gong Department of Computer Science Queen Mary, University of London, London, E1 4NS Abstract In this work, boosting the efficiency of
Image Segmentation and Registration
Image Segmentation and Registration Dr. Christine Tanner ([email protected]) Computer Vision Laboratory, ETH Zürich Dr. Verena Kaynig, Machine Learning Laboratory, ETH Zürich Outline Segmentation
A Comparison of Keypoint Descriptors in the Context of Pedestrian Detection: FREAK vs. SURF vs. BRISK
A Comparison of Keypoint Descriptors in the Context of Pedestrian Detection: FREAK vs. SURF vs. BRISK Cameron Schaeffer Stanford University CS Department [email protected] Abstract The subject of keypoint
Video Surveillance System for Security Applications
Video Surveillance System for Security Applications Vidya A.S. Department of CSE National Institute of Technology Calicut, Kerala, India V. K. Govindan Department of CSE National Institute of Technology
Discovering objects and their location in images
Discovering objects and their location in images Josef Sivic Bryan C. Russell Alexei A. Efros Andrew Zisserman William T. Freeman Dept. of Engineering Science CS and AI Laboratory School of Computer Science
A fast multi-class SVM learning method for huge databases
www.ijcsi.org 544 A fast multi-class SVM learning method for huge databases Djeffal Abdelhamid 1, Babahenini Mohamed Chaouki 2 and Taleb-Ahmed Abdelmalik 3 1,2 Computer science department, LESIA Laboratory,
Comparison of Non-linear Dimensionality Reduction Techniques for Classification with Gene Expression Microarray Data
CMPE 59H Comparison of Non-linear Dimensionality Reduction Techniques for Classification with Gene Expression Microarray Data Term Project Report Fatma Güney, Kübra Kalkan 1/15/2013 Keywords: Non-linear
Tensor Methods for Machine Learning, Computer Vision, and Computer Graphics
Tensor Methods for Machine Learning, Computer Vision, and Computer Graphics Part I: Factorizations and Statistical Modeling/Inference Amnon Shashua School of Computer Science & Eng. The Hebrew University
A Simple Introduction to Support Vector Machines
A Simple Introduction to Support Vector Machines Martin Law Lecture for CSE 802 Department of Computer Science and Engineering Michigan State University Outline A brief history of SVM Large-margin linear
COPYRIGHTED MATERIAL. Contents. List of Figures. Acknowledgments
Contents List of Figures Foreword Preface xxv xxiii xv Acknowledgments xxix Chapter 1 Fraud: Detection, Prevention, and Analytics! 1 Introduction 2 Fraud! 2 Fraud Detection and Prevention 10 Big Data for
Lecture 6: Classification & Localization. boris. [email protected]
Lecture 6: Classification & Localization boris. [email protected] 1 Agenda ILSVRC 2014 Overfeat: integrated classification, localization, and detection Classification with Localization Detection. 2 ILSVRC-2014
Learning Mid-Level Features For Recognition
Learning Mid-Level Features For Recognition Y-Lan Boureau 1,3,4 Francis Bach 1,4 Yann LeCun 3 Jean Ponce 2,4 1 INRIA 2 Ecole Normale Supérieure 3 Courant Institute, New York University Abstract Many successful
Support Vector Machines Explained
March 1, 2009 Support Vector Machines Explained Tristan Fletcher www.cs.ucl.ac.uk/staff/t.fletcher/ Introduction This document has been written in an attempt to make the Support Vector Machines (SVM),
Signature Segmentation from Machine Printed Documents using Conditional Random Field
2011 International Conference on Document Analysis and Recognition Signature Segmentation from Machine Printed Documents using Conditional Random Field Ranju Mandal Computer Vision and Pattern Recognition
Application of Event Based Decision Tree and Ensemble of Data Driven Methods for Maintenance Action Recommendation
Application of Event Based Decision Tree and Ensemble of Data Driven Methods for Maintenance Action Recommendation James K. Kimotho, Christoph Sondermann-Woelke, Tobias Meyer, and Walter Sextro Department
L25: Ensemble learning
L25: Ensemble learning Introduction Methods for constructing ensembles Combination strategies Stacked generalization Mixtures of experts Bagging Boosting CSCE 666 Pattern Analysis Ricardo Gutierrez-Osuna
E-commerce Transaction Anomaly Classification
E-commerce Transaction Anomaly Classification Minyong Lee [email protected] Seunghee Ham [email protected] Qiyi Jiang [email protected] I. INTRODUCTION Due to the increasing popularity of e-commerce
Principled Hybrids of Generative and Discriminative Models
Principled Hybrids of Generative and Discriminative Models Julia A. Lasserre University of Cambridge Cambridge, UK [email protected] Christopher M. Bishop Microsoft Research Cambridge, UK [email protected]
BRIEF: Binary Robust Independent Elementary Features
BRIEF: Binary Robust Independent Elementary Features Michael Calonder, Vincent Lepetit, Christoph Strecha, and Pascal Fua CVLab, EPFL, Lausanne, Switzerland e-mail: [email protected] Abstract.
Deformable Part Models with CNN Features
Deformable Part Models with CNN Features Pierre-André Savalle 1, Stavros Tsogkas 1,2, George Papandreou 3, Iasonas Kokkinos 1,2 1 Ecole Centrale Paris, 2 INRIA, 3 TTI-Chicago Abstract. In this work we
Assessment. Presenter: Yupu Zhang, Guoliang Jin, Tuo Wang Computer Vision 2008 Fall
Automatic Photo Quality Assessment Presenter: Yupu Zhang, Guoliang Jin, Tuo Wang Computer Vision 2008 Fall Estimating i the photorealism of images: Distinguishing i i paintings from photographs h Florin
Statistical Models in Data Mining
Statistical Models in Data Mining Sargur N. Srihari University at Buffalo The State University of New York Department of Computer Science and Engineering Department of Biostatistics 1 Srihari Flood of
